毕设帮助，选题指导，技术解答，欢迎打扰，见B站个人主页
https://space.bilibili.com/33886978
# 读取数据df = pd.read_csv('data.csv')df.head()
df.info()
print('去重前：',df.shape[0],'行数据')print('去重后：',df.drop_duplicates().shape[0],'行数据')
print(np.sum(df.isnull()))
df['date'] = df['date'].astype('datetime64[ns]')df['real_time'] = df['real_time'].astype('datetime64[ns]')df['uid'] = df['uid'].astype('str')df['user_city'] = df['user_city'].astype('str')df['user_city'] = df['user_city'].apply(lambda x:x[:-2])df['item_id'] = df['item_id'].astype('str')df['author_id'] = df['author_id'].astype('str')df['item_city'] = df['item_city'].astype('str')df['item_city'] = df['item_city'].apply(lambda x:x[:-2])df['music_id'] = df['music_id'].astype('str')df['music_id'] = df['music_id'].apply(lambda x:x[:-2])
df.info()
user_city_count = user_info.groupby(['user_city']).count().sort_values(by=['uid'],ascending=False)x1 = list(user_city_count.index)y1 = user_city_count['uid'].tolist()len(y1)
#柱形图代码chart = Bar()chart.add_xaxis(x1)chart.add_yaxis('地区使用人数', y1, color='#F6325A', itemstyle_opts={'barBorderRadius':[60, 60, 20, 20]}, label_opts=opts.LabelOpts(position='top'))chart.set_global_opts(datazoom_opts=opts.DataZoomOpts( range_start=0,range_end=5,orient='horizontal',type_='slider',is_zoom_lock=False, pos_left='1%' ), visualmap_opts=opts.VisualMapOpts(is_show = False,type_='opacity',range_opacity=[0.2, 1]), title_opts=opts.TitleOpts(title="不同地区用户数量分布图",pos_left='40%'), legend_opts=opts.LegendOpts(pos_right='10%',pos_top='2%'))chart.render_notebook()
h_num = round((df.groupby(['H']).count()['uid']/10000),1).to_list()h = list(df.groupby(['H']).count().index)
chart = Line()chart.add_xaxis(h)chart.add_yaxis('观看数/(万)',h_num, areastyle_opts=opts.AreaStyleOpts(color = '#1AF5EF',opacity=0.3), itemstyle_opts=opts.ItemStyleOpts(color='black'), label_opts=opts.LabelOpts(font_size=12))chart.set_global_opts(legend_opts=opts.LegendOpts(pos_right='10%',pos_top='2%'), title_opts=opts.TitleOpts(title="不时间观看数量分布图",pos_left='40%'),)chart.render_notebook()
left = df.groupby(['H']).sum()[['finish','like']]right = df.groupby(['H']).count()['uid']per = pd.concat([left,right],axis=1)per['finish_radio'] = round(per['finish']*100/per['uid'],2)per['like_radio'] = round(per['like']*100/per['uid'],2)x = list(df.groupby(['H']).count().index)y1 = per['finish_radio'].to_list()y2 = per['like_radio'].to_list()#建立一个基础的图形chart1 = Line()chart1.add_xaxis(x)chart1.add_yaxis('完播率/%',y1,is_smooth=True,label_opts=opts.LabelOpts(is_show=False),is_symbol_show = False, linestyle_opts=opts.LineStyleOpts(color='#F6325A',opacity=.7,curve=0,width=2,type_= 'solid' ))chart1.set_global_opts(yaxis_opts = opts.AxisOpts(min_=25,max_=45))chart1.extend_axis(yaxis=opts.AxisOpts(min_=0.4,max_=3))#叠加折线图chart2 = Line() chart2.add_xaxis(x)chart2.add_yaxis('点赞率/%',y2,yaxis_index=1,is_smooth=True,label_opts=opts.LabelOpts(is_show=False),is_symbol_show = False, linestyle_opts=opts.LineStyleOpts(color='#1AF5EF',opacity=.7,curve=0,width=2,type_= 'solid' ))chart1.overlap(chart2) chart1.set_global_opts(legend_opts=opts.LegendOpts(pos_right='10%',pos_top='2%'), title_opts=opts.TitleOpts(title="点赞/完播率分布图",pos_left='40%'),)chart1.render_notebook()
df['weekday'] = df['date'].dt.weekdayweek = df.groupby(['weekday']).count()['uid'].to_list()df_pair = [['周一', week[0]], ['周二', week[1]], ['周三', week[2]], ['周四', week[3]], ['周五', week[4]], ['周六', week[5]], ['周日', week[6]]]chart = Pie()chart.add('', df_pair,radius=['40%', '70%'],rosetype='radius',center=['45%', '50%'],label_opts=opts.LabelOpts(is_show=True,formatter = '{b}:{c}次'))chart.set_global_opts(visualmap_opts=[opts.VisualMapOpts(min_=200000,max_=300000,type_='color', range_color=['#1AF5EF', '#F6325A', '#000000'],is_show=True,pos_top='65%')], legend_opts=opts.LegendOpts(pos_right='10%',pos_top='2%',orient='vertical'), title_opts=opts.TitleOpts(title="一周内播放分布图",pos_left='35%'),)chart.render_notebook()
df.groupby(['channel']).count()['uid']
author_info = df.drop_duplicates(['author_id','item_city'])[['author_id','item_city']]author_info.info()author_city_count = author_info.groupby(['item_city']).count().sort_values(by=['author_id'],ascending=False)x1 = list(author_city_count.index)y1 = author_city_count['author_id'].tolist()df.drop_duplicates(['author_id']).shape[0]
chart = Bar()chart.add_xaxis(x1)chart.add_yaxis('地区创作者人数', y1, color='#F6325A', itemstyle_opts={'barBorderRadius':[60, 60, 20, 20]})chart.set_global_opts(datazoom_opts=opts.DataZoomOpts( range_start=0,range_end=5,orient='horizontal',type_='slider',is_zoom_lock=False, pos_left='1%' ), visualmap_opts=opts.VisualMapOpts(is_show = False,type_='opacity',range_opacity=[0.2, 1]), legend_opts=opts.LegendOpts(pos_right='10%',pos_top='2%'), title_opts=opts.TitleOpts(title="不同城市创作者分布图",pos_left='40%'))chart.render_notebook()
time = df.drop_duplicates(['item_id'])[['item_id','duration_time']]time = time.groupby(['duration_time']).count()x1 = list(time.index)y1 = time['item_id'].tolist()
chart = Bar()chart.add_xaxis(x1)chart.add_yaxis('视频时长对应视频数', y1, color='#1AF5EF', itemstyle_opts={'barBorderRadius':[60, 60, 20, 20]}, label_opts=opts.LabelOpts(font_size=12, color='black'))chart.set_global_opts(datazoom_opts=opts.DataZoomOpts( range_start=0,range_end=50,orient='horizontal',type_='slider'), visualmap_opts=opts.VisualMapOpts(max_=100000,min_=200,is_show = False,type_='opacity',range_opacity=[0.4, 1]), legend_opts=opts.LegendOpts(pos_right='10%',pos_top='2%'), title_opts=opts.TitleOpts(title="不同时长作品分布图",pos_left='40%'))chart.render_notebook()
like_per = 100*np.sum(df['like'])/len(df['like'])finish_per = 100*np.sum(df['finish'])/len(df['finish'])gauge = Gauge()gauge.add("",[("视频互动率", like_per),['完播率',finish_per]],detail_label_opts=opts.LabelOpts(is_show=False,font_size=18), axisline_opts=opts.AxisLineOpts(linestyle_opts=opts.LineStyleOpts( color=[(0.3, "#1AF5EF"), (0.7, "#F6325A"), (1, "#000000")],width=20)))gauge.render_notebook()
df_cor = df[['finish','like','duration_time','H']] # 只选取部分cor_table = df_cor.corr(method='spearman')cor_array = np.array(cor_table)cor_name = list(cor_table.columns)value = [[i, j, cor_array[i,j]] for i in [3,2,1,0] for j in [0,1,2,3]] heat = HeatMap()heat.add_xaxis(cor_name)heat.add_yaxis("",cor_name,value,label_opts=opts.LabelOpts(is_show=True, position="inside"))heat.set_global_opts(visualmap_opts=opts.VisualMapOpts(is_show=False, max_=0.08, range_color=["#1AF5EF", "#F6325A", "#000000"]))heat.render_notebook()
temp = df['date'].to_list()puv = df.groupby(['date']).agg({'uid':'nunique','item_id':'count'})uv = puv['uid'].to_list()pv = puv['item_id'].to_list()time = puv.index.to_list()chart1 = Line()chart1.add_xaxis(time)chart1.add_yaxis('uv',uv,is_smooth=True,label_opts=opts.LabelOpts(is_show=False),is_symbol_show = False, linestyle_opts=opts.LineStyleOpts(color='#1AF5EF',opacity=.7,curve=0,width=2,type_= 'solid' ))chart1.add_yaxis('pv',pv,is_smooth=True,label_opts=opts.LabelOpts(is_show=False),is_symbol_show = False, linestyle_opts=opts.LineStyleOpts(color='#F6325A',opacity=.7,curve=0,width=2,type_= 'solid' ))chart1.render_notebook()
lc = []for i in range(len(time)-7): bef = set(list(df[df['date']==time[i]]['uid'])) aft = set(list(df[df['date']==time[i+7]]['uid'])) stay = bef&aft per = round(100*len(stay)/len(bef),2) lc.append(per) lc1 = []for i in range(len(time)-1): bef = set(list(df[df['date']==time[i]]['uid'])) aft = set(list(df[df['date']==time[i+1]]['uid'])) stay = bef&aft per = round(100*len(stay)/len(bef),2) lc1.append(per)x7 = time[0:-7]chart1 = Line()chart1.add_xaxis(x7)chart1.add_yaxis('七日留存率/%',lc,is_smooth=True,label_opts=opts.LabelOpts(is_show=False),is_symbol_show = False, linestyle_opts=opts.LineStyleOpts(color='#F6325A',opacity=.7,curve=0,width=2,type_= 'solid' ))chart1.set_global_opts(legend_opts=opts.LegendOpts(pos_right='10%',pos_top='2%'), title_opts=opts.TitleOpts(title="用户留存率分布图",pos_left='40%'),)chart1.render_notebook()
df1 = df.groupby(['uid']).agg({'item_id':'count','like':'sum','finish':'sum'})df1['like_per'] = df1['like']/df1['item_id']df1['finish_per'] = df1['finish']/df1['item_id']ndf1 = np.array(df1[['item_id','like_per','finish_per']])#.shapekmeans_per_k = [KMeans(n_clusters=k).fit(ndf1) for k in range(1,8)]inertias = [model.inertia_ for model in kmeans_per_k]chart = Line(init_opts=opts.InitOpts(width='560px',height='300px'))chart.add_xaxis(range(1,8))chart.add_yaxis("",inertias,label_opts=opts.LabelOpts(is_show=False), linestyle_opts=opts.LineStyleOpts(color='#F6325A',opacity=.7,curve=0,width=3,type_= 'solid' ))chart.render_notebook()
n_cluster = 4cluster = KMeans(n_clusters=n_cluster,random_state=0).fit(ndf1)y_pre = cluster.labels_ # 查看聚好的类from sklearn.metrics import silhouette_scorefrom sklearn.metrics import silhouette_samplessilhouette_score(ndf1,y_pre) n_cluster = 3cluster = KMeans(n_clusters=n_cluster,random_state=0).fit(ndf1)y_pre = cluster.labels_ # 查看聚好的类from sklearn.metrics import silhouette_scorefrom sklearn.metrics import silhouette_samplessilhouette_score(ndf1,y_pre)
c_ = [[],[],[]]c_[0] = [87.998,9.1615,39.92]c_[1] = [13.292,12.077,50.012]c_[2] = [275.011,8.125,28.751]bar = Bar(init_opts=opts.InitOpts(theme='macarons',width='1000px',height='400px')) # 添加分类（x轴）的数据bar.add_xaxis(['播放数','点赞率(千分之)','完播率(百分之)'])bar.add_yaxis('0', [round(i,2) for i in c_[0]], stack='stack0') bar.add_yaxis('1',[round(i,2) for i in c_[1]], stack='stack1') bar.add_yaxis('2',[round(i,2) for i in c_[2]], stack='stack2') bar.render_notebook()
毕设帮助，选题指导，技术解答，欢迎打扰，见B站个人主页